接着这篇文章Node.js+jade抓取博客所有文章生成静态html文件的实例继续,在这篇文章中实现了采集与静态文件的生成,在实际的采集项目中, 应该是先入库再选择性的生成静态文件。
那么我选择的数据库是mongodb,为什么用这个数据库,因为这个数据库是基于集合,数据的操作基本是json,与dom模块cheerio具有非常大的亲和力,cheerio处理过滤出来的数据,可以直接插入mongodb,不需要经过任何的处理,非常的便捷,当然跟node.js的亲和力那就不用说了,更重要的是,性能很棒。这篇文章我就不具体写mongodb的基本用法,到时候会另起文章从0开始写mongodb基本常用用法.先看下入库的效果与生成静态文件的效果:
我在这个阶段,把爬虫分离成2个模块,采集入库( crawler.js ), 生成静态文件(makeHtml.js).
crawler.js:
var http = require('http'); var cheerio = require('cheerio'); var mongoose = require('mongoose'); mongoose.Promise = global.Promise; var DB_URL = 'mongodb://localhost:27017/crawler'; var aList = []; //博客文章列表信息 var aUrl = []; //博客所有的文章url var db = mongoose.createConnection(DB_URL); db.on('connected', function (err) { if (err) { console.log(err); } else { console.log('db connected success'); } }); var Schema = mongoose.Schema; var arcSchema = new Schema({ id: Number, //文章id title: String, //文章标题 url: String, //文章链接 body: String, //文章内容 entry: String, //摘要 listTime: Date //发布时间 }); var Article = db.model('Article', arcSchema); function saveArticle(arcInfo) { var arcModel = new Article(arcInfo); arcModel.save(function (err, result) { if (err) { console.log(err); } else { console.log(`${arcInfo['title']} 插入成功`); } }); } function filterArticle(html) { var $ = cheerio.load(html); var arcDetail = {}; var title = $("#cb_post_title_url").text(); var href = $("#cb_post_title_url").attr("href"); var re = /\/(\d+)\.html/; var id = href.match(re)[1]; var body = $("#cnblogs_post_body").html(); return { id: id, title: title, url: href, body: body }; } function crawlerArc(url) { var html = ''; var str = ''; var arcDetail = {}; http.get(url, function (res) { res.on('data', function (chunk) { html += chunk; }); res.on('end', function () { arcDetail = filterArticle(html); saveArticle(arcDetail); if ( aUrl.length ) { setTimeout(function () { if (aUrl.length) { crawlerArc(aUrl.shift()); } }, 100); }else { console.log( '采集任务完成' ); return; } }); }); } function filterHtml(html) { var $ = cheerio.load(html); var arcList = []; var aPost = $("#content").find(".post-list-item"); aPost.each(function () { var ele = $(this); var title = ele.find("h2 a").text(); var url = ele.find("h2 a").attr("href"); ele.find(".c_b_p_desc a").remove(); var entry = ele.find(".c_b_p_desc").text(); ele.find("small a").remove(); var listTime = ele.find("small").text(); var re = /\d{4}-\d{2}-\d{2}\s*\d{2}[:]\d{2}/; listTime = listTime.match(re)[0]; arcList.push({ title: title, url: url, entry: entry, listTime: listTime }); }); return arcList; } function nextPage(html) { var $ = cheerio.load(html); var nextUrl = $("#pager a:last-child").attr('href'); if (!nextUrl) return getArcUrl(aList); var curPage = $("#pager .current").text(); if (!curPage) curPage = 1; var nextPage = nextUrl.substring(nextUrl.indexOf('=') + 1); if (curPage < nextPage) crawler(nextUrl); } function crawler(url) { http.get(url, function (res) { var html = ''; res.on('data', function (chunk) { html += chunk; }); res.on('end', function () { aList.push(filterHtml(html)); nextPage(html); }); }); } function getArcUrl(arcList) { for (var key in arcList) { for (var k in arcList[key]) { aUrl.push(arcList[key][k]['url']); } } crawlerArc(aUrl.shift()); } var url = 'http://www.cnblogs.com/ghostwu/'; crawler(url);
其他的核心模块没有怎么改动,主要增加了数据库连接,数据库创建,集合创建( 集合相当于关系型数据库中的表 ),Schema( 相当于关系型数据库的表结构 ).
mongoose操作数据库( save:插入数据 ).分离了文件生成模块.
makeHtml.js文件
var fs = require('fs'); var jade = require('jade'); var mongoose = require('mongoose'); mongoose.Promise = global.Promise; var DB_URL = 'mongodb://localhost:27017/crawler'; var allArc = []; var count = 0; var db = mongoose.createConnection(DB_URL); db.on('connected', function (err) { if (err) { console.log(err); } else { console.log('db connected success'); } }); var Schema = mongoose.Schema; var arcSchema = new Schema({ id: Number, //文章id title: String, //文章标题 url: String, //文章链接 body: String, //文章内容 entry: String, //摘要 listTime: Date //发布时间 }); var Article = db.model('Article', arcSchema); function makeHtml(arcDetail) { str = jade.renderFile('./views/layout.jade', arcDetail); ++count; fs.writeFile('./html/' + count + '.html', str, function (err) { if (err) { console.log(err); } console.log( `${arcDetail['id']}.html创建成功` + count ); if ( allArc.length ){ setTimeout( function(){ makeHtml( allArc.shift() ); }, 100 ); } }); } function getAllArc(){ Article.find( {}, function( err, arcs ){ allArc = arcs; makeHtml( allArc.shift() ); } ).sort( { 'id' : 1 } ); } getAllArc();
以上这篇Node.js+jade+mongodb+mongoose实现爬虫分离入库与生成静态文件的方法就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。